parsing XML file with "&<" characters when using python lxml

Question

I have a xml file, some of it's tags has some characters like "ç". What I want is to extract this tag's text and write into .txt file.

Here is the xml file look's like:

    
<article mdate="2020-04-16" key="journals/tkdd/DuarteGB16">
<author>Jo&atilde;o Duarte</author>
<author orcid="0000-0003-3357-1195">Jo&atilde;o Gama</author>
<author orcid="0000-0002-8339-7773">Albert Bifet</author>
<title>Adaptive Model Rules From High-Speed Data Streams.</title>
<pages>30:1-30:22</pages>
<year>2016</year>
<volume>10</volume>
<journal>ACM Trans. Knowl. Discov. Data</journal>
<number>3</number>
<ee>https://doi.org/10.1145/2829955</ee>
<ee>https://www.wikidata.org/entity/Q58204491</ee>
<url>db/journals/tkdd/tkdd10.html#DuarteGB16</url>
</article>

and here is my code in python:

import lxml.etree as ET

import os
from pathlib import Path


test_file = "test_data.xml"
file_output_path = "results.txt"


def search_xxx(root, sth: str, file_writer):

    """
    parameter: [sth] can be article、inproceedings、proceedings、book、incollection、phdthesis、mastersthesis、www

    """
    # with open("result.txt", "w") as f:


    item_counter = 0

    for item in root.findall(sth):

        message = []
        invalid = False

        item_counter += 1


        
        # print("-----info---------")
        # article dict["key"] -> key
        key_str = item.attrib["key"] 
        key_str_list = key_str.split('/')
        key = key_str_list[1]

        # print("[Category]: ", key_str)
        message.append(key)
        

        # key_str = item.attrib["key"]
        # message.append(key_str)


        # title
        if item.find("title") != None:
            if item.find("title").text != None:
                title = item.find("title").text

                # print("[Title]: ", title)
                message.append(title)
            else:
                # invalid = True
                continue
        else:
            invalid = True


        # author 
        # print("[Authors]:")
        for item_son in item.iter("author"):
            if item_son.text != None:

                # author = item_son.text
                author = item_son.text
                # print("[author]: ", author)
        

                message.append(author)
            else:
                invalid = True
                break
                
        

        ## write to file
        # print(message)
        # print()

        if invalid == True:
            # message = ""
            file_writer.write("")
        else:

    
            message = "+".join(message)
            

            file_writer.write(message + '\n')
            # print("---------------")
    


# write to txt file.

def main():

    parser = ET.XMLParser(recover=True)
    # tree = ET.parse(test_file, parser=parser)
    tree = ET.parse(dblp_file_path, parser=parser)

    root = tree.getroot()

    with open(file_output_path, "w", encoding="UTF-8") as f:
        print("Extracting...")
        
        search_xxx(root, "article", f)

        print("Extract done.")


if __name__ == "__main__":
    main()

Question: when I run this code and it will get the expected result:

output: tkdd+Adaptive Model Rules From High-Speed Data Streams.+Jo+Jo+Albert Bifet

Here comes the question:

in XML file,

<author>Jo&atilde;o Duarte</author>
<author orcid="0000-0003-3357-1195">Jo&atilde;o Gama</author>

I want to get the first author which should be "Joo Duarte", the second should be "Joo Gama",

But, the result is "Jo" and "Jo".

Can someone help me out, PLEASE!